© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7796
    Prev
    Next
    INDEX
    Explanations

    mentions of current events, particularly those involving politics and societal issues

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     have
    -0.97
    have
    -0.96
    Have
    -0.90
     دیکھیے
    -0.81
     Have
    -0.79
     متعلقه
    -0.77
     estimés
    -0.77
     femininas
    -0.75
     haue
    -0.75
     Wikimedijinoj
    -0.72
    POSITIVE LOGITS
     has
    1.17
    Has
    0.63
     Has
    0.61
    has
    0.57
    ExecuteReader
    0.46
     heeft
    0.46
    ComponentModel
    0.43
    arak
    0.42
    去吧
    0.40
    ini
    0.40
    Activations Density 2.405%

    No Known Activations